IBM P690A Regatta (Power 4 Dual Core Chip)

詳細說明
System Hardware Configuration
1. Hostname : ivan1~ivan4
2. Model Name : IBM pSeries 690 Turbo 1.9 GHz
3. CPU :
- Number : 32 per node ( Dual Core per Chip )
- Model : Power 4+ Chip (64 Bit)
- Clock Rate : 1.9 GHz
- Archtecture: SMP
- Integer Peak Performance: SPECcint2000 : 1786 ( per CPU)
- Floating Peak Performance: SPECcfp2000 : 1898( per CPU )
- Global Performance: ( Linpack )
Rmax : 415.2 GFLOPS ( 96 CPUs )
Rpeak : 729.6 GFLOPS ( 96 CPUs )
4. L1 Cache (per CPU)
- Instruction/Data: 32KB/64KB
- Organization: Direct map, 128-byte line(instruction)
- Two-way, 128-byte line(data)
- Capacity : 128 KB per chip (64KB per processor)
5. L2 Cache (per chip)
- Size : 1.4 MB
- Bandwidth : Shared 124.8 GB/sec
- Organization: Eight-way, 128-byte line
6. L3 Cache ( per MCM)
- Size : Shared 32 MB/chip (128MB/8-way module)
- Bandwidth : Shared 13.9 GB/sec
- Organization: Eight-way , 512-byte line, managed as four 128-byte sectors
7. Internal System Bandwidth: 12.8GB/sec ( x 16 = 205 GB/sec for 32-way )
8. Main Memory:
- Type : Shared Nothing
- Capability : 192 Gbyte ( 64 GB per node )
9. Physical Disks
- Internal: 18 GB x 2
10. Major Directories
- /u1 : 68 GB
- /u2 : 921 GB
- /package1 : 256GB
- /work1: 1088 GB
- /work2: 1024 GB
- /scratch : 34 GB * 3 nodes
11. Peripherals
- Internal: 4mm Tape Drive and DVD-ROM
12. Graphics
- Accelerator: N/A
- Bit-Planes: N/A
13. Job Submission
- Interactive: yes ( 1 hrs limits)
- Batch: LoadLeveler
- LoadLeveler 使用簡介
14. Installation/Upgrade Records
- 2004/11 : install AIX 5.2L , PSSP 3.5
15. Documentions
16. More Information
NCHC Consulting Window
Mr. Sheng Chung Lu (03)5776085 # 205
a00scl00@nchc.org.tw
NCHC P690 User Computing Environment

LoadLeveler Queuing System:
| IBM P690 Regatta Configuration of batch classes | |||||
|---|---|---|---|---|---|
| Class | CPU Time Limit(hr.) | Nodes | Spool | CPU-Mode | Max slots for Running |
| serial | 168 | 1 | ivan1 | P690 Power4 1.9GHz Turbo | 28 |
| 4cpu | 96 | 3 | ivan1,3,4 | P690 Power4 1.9GHz Turbo | 80 |
| 8cpu | 72 | 3 | ivan1,3,4 | P690 Power4 1.9GHz Turbo | 80 |
| 16cpu | 72 | 2 | ivan3,4 | P690 Power4 1.9GHz Turbo | 64 |
| Interactive nodes | 1 | 1 | ivan2 | P690 Power4 1.9GHz Turbo | |
| mono | 若以上計算量仍無法滿足需求,需要特殊申請經計算資源委員會通過,方可使用 | ||||
System Software
- AIX 5.2 64bit version
- PSSP 3.5
- LoadLevel 3.2
- Fortran 77/90 8.1
- IBM C Language 6.0
- IBM C++ Language 6.0
- VisualAge C++ 6.0
Application Packages
Most of application package on system are placed in /package1 directory. You may get further information for application packages list at http://www.nchc.org.tw/tw/services/software_database.php
Disk usage Constrained Policy :
- /tmp : clear files not accessed over 1 day.
- /work1 : clear files not accessed over 2 week.
- /work2 : clear files not accessed over 2 week.
- /scratch : clear files not accessed over 1 day.( only apply in computing node )
NCHC reverses the right to change/reconfigure/destroy these working filesystem without any backup.
IBM Compiler Command
1. C for AIX Compiler Command:
"xlc" , “xlc_r” , "cc" , “cc_r”...
2. VisualAge C++ Compiler : (eg: xxx.C)
"xlC" ,"xlC_r"
3. XL Fortran for AIX :
"xlf" , "f77" , "xlf_r" , "xlf90"...
4. MPI for C :
"mpcc" , "mpcc_r"
5. MPI for C++ : (eg: xxx.C)
"mpCC" ,"mpCC_r"
6. MPI for Fortran
"mpxlf" , "mpxlf90" , "mpxlf90_r"...
example :
Source file : run.C
Execute file : run.exe
mpCC -o run.exe run.C
Detail refer to
http://www.nersc.gov/vendor_docs/ibm/pe/am102mst02.html
A. Compiler Options - Performance:
1. Tyep of RS/6000 System : “–qarch=[architechture]”
-qarch=pwr2 (IBM power 2 chip) [ivy system]
-qarch=pwr3 (IBM power 3 chip) [ivory system]
-qarch=pwr4 (IBM power 4 chip, now the compiler version did not support yet) [imp system]
2. Tuning for specific system : “-qtune=[implementation]”
-qtune= pwr2 (IBM power 2 chip) [ivy system]
-qtune= pwr3 (IBM power 3 chip) [ivory system]
-qtune= pwr4 (IBM power 4 chip, now the compiler version did not support yet) [imp system]
3. Optimization Level ( -O,-O2, -O3, -O4 )
Deault : no optimization
-O3 is desired setting
Use –qstrict ( When –O3 –qhot ) to restrict semantic alteration
-O4 implied –O3 –qhot –qipa (only for wall struct)
B. Compiler Options – Data
1. Default Data type are 32-bit
- REAL*4,Complex*8
- Integer*4
- Logical*4
2. 64-bit Floation Poing Repersentation (-qrealsize=bytes)
- -qrealsize=8 for double precision (64-bit)
3. 64-bit mode ( -q64 )
4. Specify the maximum user data area ( -bmaxdata )
- In 32-bit mode, the default maximum user data area is 256MB.
- -bmaxdata:0x10000000 (default)
- -bmaxdata:0x80000000 (get eight 256MB segments, 2GB)
5. Specify the maximum space for the program stack area
- For automatic data area
- -bmaxstack= to overcome soft limit on stack size
- Maximun allowed value is 256MB for 32-bit mode
More Detail XL Fortran info refer to
http://www-3.ibm.com/software/ad/fortran/xlfortran/
More Detail C Language info refer to
http://www-3.ibm.com/software/ad/vacpp/






